Supervised machine learning techniques to the prediction of tunnel boring machine penetration rate
Predicting the penetration rate is a complex and challenging task due to the interaction between the tunnel boring machine (TBM) and the rock mass. Many studies highlight the use of empirical and theoretical techniques in predicting TBM performance. However, reliable performance prediction of TBM is...
Main Authors: | , , , , |
---|---|
Format: | Article |
Language: | English |
Published: |
MDPI AG
2019
|
Subjects: | |
Online Access: | http://eprints.utm.my/88666/1/MahmoodMdTahir2019_SupervisedMachineLearningTechniquestothePrediction.pdf |
_version_ | 1796864675390947328 |
---|---|
author | Xu, Hai Zhou, Jian Asteris, Panagiotis G. Armaghani, Danial Jahed Md. Tahir, Mahmood |
author_facet | Xu, Hai Zhou, Jian Asteris, Panagiotis G. Armaghani, Danial Jahed Md. Tahir, Mahmood |
author_sort | Xu, Hai |
collection | ePrints |
description | Predicting the penetration rate is a complex and challenging task due to the interaction between the tunnel boring machine (TBM) and the rock mass. Many studies highlight the use of empirical and theoretical techniques in predicting TBM performance. However, reliable performance prediction of TBM is of crucial importance to mining and civil projects as it can minimize the risks associated with capital costs. This study presents new applications of supervised machine learning techniques, i.e., k-nearest neighbor (KNN), chi-squared automatic interaction detection (CHAID), support vector machine (SVM), classification and regression trees (CART) and neural network (NN) in predicting the penetration rate (PR) of a TBM. To achieve this aim, an experimental database was set up, based on field observations and laboratory tests for a tunneling project in Malaysia. In the database, uniaxial compressive strength, Brazilian tensile strength, rock quality designation, weathering zone, thrust force, and revolution per minute were utilized as inputs to predict PR of TBM. Then, KNN, CHAID, SVM, CART, and NN predictive models were developed to select the best one. A simple ranking technique, as well as some performance indices, were calculated for each developed model. According to the obtained results, KNN received the highest-ranking value among all five predictive models and was selected as the best predictive model of this study. It can be concluded that KNN is able to provide high-performance capacity in predicting TBM PR. KNN model identified uniaxial compressive strength (0.2) as the most important and revolution per minutes (0.14) as the least important factor for predicting the TBM penetration rate. |
first_indexed | 2024-03-05T20:45:25Z |
format | Article |
id | utm.eprints-88666 |
institution | Universiti Teknologi Malaysia - ePrints |
language | English |
last_indexed | 2024-03-05T20:45:25Z |
publishDate | 2019 |
publisher | MDPI AG |
record_format | dspace |
spelling | utm.eprints-886662020-12-15T10:39:16Z http://eprints.utm.my/88666/ Supervised machine learning techniques to the prediction of tunnel boring machine penetration rate Xu, Hai Zhou, Jian Asteris, Panagiotis G. Armaghani, Danial Jahed Md. Tahir, Mahmood TA Engineering (General). Civil engineering (General) Predicting the penetration rate is a complex and challenging task due to the interaction between the tunnel boring machine (TBM) and the rock mass. Many studies highlight the use of empirical and theoretical techniques in predicting TBM performance. However, reliable performance prediction of TBM is of crucial importance to mining and civil projects as it can minimize the risks associated with capital costs. This study presents new applications of supervised machine learning techniques, i.e., k-nearest neighbor (KNN), chi-squared automatic interaction detection (CHAID), support vector machine (SVM), classification and regression trees (CART) and neural network (NN) in predicting the penetration rate (PR) of a TBM. To achieve this aim, an experimental database was set up, based on field observations and laboratory tests for a tunneling project in Malaysia. In the database, uniaxial compressive strength, Brazilian tensile strength, rock quality designation, weathering zone, thrust force, and revolution per minute were utilized as inputs to predict PR of TBM. Then, KNN, CHAID, SVM, CART, and NN predictive models were developed to select the best one. A simple ranking technique, as well as some performance indices, were calculated for each developed model. According to the obtained results, KNN received the highest-ranking value among all five predictive models and was selected as the best predictive model of this study. It can be concluded that KNN is able to provide high-performance capacity in predicting TBM PR. KNN model identified uniaxial compressive strength (0.2) as the most important and revolution per minutes (0.14) as the least important factor for predicting the TBM penetration rate. MDPI AG 2019-09 Article PeerReviewed application/pdf en http://eprints.utm.my/88666/1/MahmoodMdTahir2019_SupervisedMachineLearningTechniquestothePrediction.pdf Xu, Hai and Zhou, Jian and Asteris, Panagiotis G. and Armaghani, Danial Jahed and Md. Tahir, Mahmood (2019) Supervised machine learning techniques to the prediction of tunnel boring machine penetration rate. Applied Sciences (Switzerland), 9 (18). p. 3715. ISSN 2076-3417 http://dx.doi.org/10.3390/app9183715 |
spellingShingle | TA Engineering (General). Civil engineering (General) Xu, Hai Zhou, Jian Asteris, Panagiotis G. Armaghani, Danial Jahed Md. Tahir, Mahmood Supervised machine learning techniques to the prediction of tunnel boring machine penetration rate |
title | Supervised machine learning techniques to the prediction of tunnel boring machine penetration rate |
title_full | Supervised machine learning techniques to the prediction of tunnel boring machine penetration rate |
title_fullStr | Supervised machine learning techniques to the prediction of tunnel boring machine penetration rate |
title_full_unstemmed | Supervised machine learning techniques to the prediction of tunnel boring machine penetration rate |
title_short | Supervised machine learning techniques to the prediction of tunnel boring machine penetration rate |
title_sort | supervised machine learning techniques to the prediction of tunnel boring machine penetration rate |
topic | TA Engineering (General). Civil engineering (General) |
url | http://eprints.utm.my/88666/1/MahmoodMdTahir2019_SupervisedMachineLearningTechniquestothePrediction.pdf |
work_keys_str_mv | AT xuhai supervisedmachinelearningtechniquestothepredictionoftunnelboringmachinepenetrationrate AT zhoujian supervisedmachinelearningtechniquestothepredictionoftunnelboringmachinepenetrationrate AT asterispanagiotisg supervisedmachinelearningtechniquestothepredictionoftunnelboringmachinepenetrationrate AT armaghanidanialjahed supervisedmachinelearningtechniquestothepredictionoftunnelboringmachinepenetrationrate AT mdtahirmahmood supervisedmachinelearningtechniquestothepredictionoftunnelboringmachinepenetrationrate |